Adaptive Keyframe Sampling for Long Video Understanding

Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a long video, the above paradigm encounters difficulty because the vast amount of video tokens has significantly exceeded the maximal capacity of MLLMs. Therefore, existing video-based MLLMs are mostly established upon sampling a small portion of tokens from input data, which can cause key information to be lost and thus produce incorrect answers. This paper presents a simple yet effective algorithm named Adaptive Keyframe Sampling (AKS). It inserts a plug-and-play module known as keyframe selection, which aims to maximize the useful information with a fixed number of video tokens. We formulate keyframe selection as an optimization involving (1) the relevance between the keyframes and the prompt, and (2) the coverage of the keyframes over the video, and present an adaptive algorithm to approximate the best solution. Experiments on two long video understanding benchmarks validate that Adaptive Keyframe Sampling improves video QA accuracy (beyond strong baselines) upon selecting informative keyframes. Our study reveals the importance of information pre-filtering in video-based MLLMs. Code is available at https://github.com/ncTimTang/AKS.

YOLOv12: Attention-Centric Real-Time Object Detectors

Enhancing the network architecture of the YOLO framework has been crucial for a long time, but has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because attention-based models cannot match the speed of CNN-based models. This paper proposes an attention-centric YOLO framework, namely YOLOv12, that matches the speed of previous CNN-based ones while harnessing the performance benefits of attention mechanisms. YOLOv12 surpasses all popular real-time object detectors in accuracy with competitive speed. For example, YOLOv12-N achieves 40.6% mAP with an inference latency of 1.64 ms on a T4 GPU, outperforming advanced YOLOv10-N / YOLOv11-N by 2.1%/1.2% mAP with a comparable speed. This advantage extends to other model scales. YOLOv12 also surpasses end-to-end real-time detectors that improve DETR, such as RT-DETR / RT-DETRv2: YOLOv12-S beats RT-DETR-R18 / RT-DETRv2-R18 while running 42% faster, using only 36% of the computation and 45% of the parameters. More comparisons are shown in Figure 1.

CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis

Accurately depicting real-world landscapes in remote sensing (RS) images requires precise alignment between objects and their environment. However, most existing synthesis methods for natural images prioritize foreground control, often reducing the background to plain textures. This neglects the interaction between foreground and background, which can lead to incoherence in RS scenarios. In this paper, we introduce CC-Diff, a Diffusion Model-based approach for RS image generation with enhanced Context Coherence. To capture spatial interdependence, we propose a sequential pipeline where background generation is conditioned on synthesized foreground instances. Distinct learnable queries are also employed to model both the complex background texture and its semantic relation to the foreground. Extensive experiments demonstrate that CC-Diff outperforms state-of-the-art methods in visual fidelity, semantic accuracy, and positional precision, excelling in both RS and natural image domains. CC-Diff also shows strong trainability, improving detection accuracy by 2.04 mAP on DOTA and 2.25 mAP on the COCO benchmark.

Mixture of Physical Priors Adapter for Parameter-Efficient Fine-Tuning

Most parameter-efficient fine-tuning (PEFT) methods rely on low-rank representations to adapt models. However, these approaches often oversimplify representations, particularly when the underlying data has high-rank or high-frequency components. This limitation hinders the model's ability to capture complex data interactions effectively. In this paper, we propose a novel approach that models network weights by leveraging a combination of physical priors, enabling more accurate approximations. We use three foundational equations -- heat diffusion, wave propagation, and Poisson's steady-state equation -- each contributing distinctive modeling properties: heat diffusion enforces local smoothness, wave propagation facilitates long-range interactions, and Poisson's equation captures global equilibrium. To combine these priors effectively, we introduce the Mixture of Physical Priors Adapter (MoPPA), using an efficient Discrete Cosine Transform (DCT) implementation. To dynamically balance these priors, a route regularization mechanism is designed to adaptively tune their contributions. MoPPA serves as a lightweight, plug-and-play module that seamlessly integrates into transformer architectures, with adaptable complexity depending on the local context. Specifically, using MAE pre-trained ViT-B, MoPPA improves PEFT accuracy by up to 2.1% on VTAB-1K image classification with a comparable number of trainable parameters, and advantages are further validated through experiments across various vision backbones, showcasing MoPPA's effectiveness and adaptability. The code will be made public available.

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly selected timesteps. However, such a strategy neglects the fact that differences among model outputs are not uniform across timesteps, which hinders selecting the appropriate model outputs to cache, leading to a poor balance between inference efficiency and visual quality. In this study, we introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps. Rather than directly using the time-consuming model outputs, TeaCache focuses on model inputs, which have a strong correlation with the modeloutputs while incurring negligible computational cost. TeaCache first modulates the noisy inputs using the timestep embeddings to ensure their differences better approximating those of model outputs. TeaCache then introduces a rescaling strategy to refine the estimated differences and utilizes them to indicate output caching. Experiments show that TeaCache achieves up to 4.41x acceleration over Open-Sora-Plan with negligible (-0.07% Vbench score) degradation of visual quality.

RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model

Remote sensing foundation models largely break away from the traditional paradigm of designing task-specific models, offering greater scalability across multiple tasks. However, they face challenges such as low computational efficiency and limited interpretability, especially when dealing with high-resolution remote sensing images. To overcome these, we draw inspiration from heat conduction, a physical process modeling local heat diffusion. Building on this idea, we are the first to explore the potential of using the parallel computing model of heat conduction to simulate the local region correlations in high-resolution remote sensing images, and introduce RS-vHeat, an efficient multi-modal remote sensing foundation model. Specifically, RS-vHeat 1) applies the Heat Conduction Operator (HCO) with a complexity of $O(N^{1.5})$ and a global receptive field, reducing computational overhead while capturing remote sensing object structure information to guide heat diffusion; 2) learns the frequency distribution representations of various scenes through a self-supervised strategy based on frequency domain hierarchical masking and multi-domain reconstruction; 3) significantly improves efficiency and performance over state-of-the-art techniques across 4 tasks and 10 datasets. Compared to attention-based remote sensing foundation models, we reduces memory consumption by 84%, decreases FLOPs by 24% and improves throughput by 2.7 times.

ClickTrack: Towards Real-time Interactive Single Object Tracking

Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single object trackers and propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. Moreover, click as an input type inherently lack hierarchical information. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs, transforming the point into the bounding box expected by the operator. The bounding box will be used as input of single object trackers. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios. Furthermore, we explored the integration of GCR into the Segment Anything model(SAM), significantly reducing ambiguity issues when SAM receives point inputs.

Click; Single Object Tracking; Video Object Segmentation; Real-time Interaction

Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single object trackers and propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. Moreover, click as an input type inherently lack hierarchical information. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs, transforming the point into the bounding box expected by the operator. The bounding box will be used as input of single object trackers. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios. Furthermore, we explored the integration of GCR into the Segment Anything model(SAM), significantly reducing ambiguity issues when SAM receives point inputs.

Vision Calorimeter for Anti-neutron Reconstruction: A Baseline

In high-energy physics, anti-neutrons ($\bar{n}$) are fundamental particles that frequently appear as final-state particles, and the reconstruction of their kinematic properties provides an important probe for understanding the governing principles. However, this confronts significant challenges instrumentally with the electromagnetic calorimeter (EMC), a typical experimental sensor but recovering the information of incident $\bar{n}$ insufficiently. In this study, we introduce Vision Calorimeter (ViC), a baseline method for anti-neutron reconstruction that leverages deep learning detectors to analyze the implicit relationships between EMC responses and incident $\bar{n}$ characteristics. Our motivation lies in that energy distributions of $\bar{n}$ samples deposited in the EMC cell arrays embody rich contextual information. Converted to 2-D images, such contextual energy distributions can be used to predict the status of $\bar{n}$ ($i.e.$, incident position and momentum) through a deep learning detector along with pseudo bounding boxes and a specified training objective. Experimental results demonstrate that ViC substantially outperforms the conventional reconstruction approach, reducing the prediction error of incident position by 42.81% (from 17.31$^{\circ}$ to 9.90$^{\circ}$). More importantly, this study for the first time realizes the measurement of incident $\bar{n}$ momentum, underscoring the potential of deep learning detectors for particle reconstruction. Code is available at https://github.com/yuhongtian17/ViC.

Depth-guided Texture Diffusion for Image Semantic Segmentation

Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and compromise accuracy due to the modality gap between the depth and the vision. In this work, we introduce a Depth-guided Texture Diffusion approach that effectively tackles the outlined challenge. Our method extracts low-level features from edges and textures to create a texture image. This image is then selectively diffused across the depth map, enhancing structural information vital for precisely extracting object outlines. By integrating this enriched depth map with the original RGB image into a joint feature embedding, our method effectively bridges the disparity between the depth map and the image, enabling more accurate semantic segmentation. We conduct comprehensive experiments across diverse, commonly-used datasets spanning a wide range of semantic segmentation tasks, including Camouflaged Object Detection (COD), Salient Object Detection (SOD), and indoor semantic segmentation. With source-free estimated depth or depth captured by depth cameras, our method consistently outperforms existing baselines and achieves new state-of-theart results, demonstrating the effectiveness of our Depth-guided Texture Diffusion for image semantic segmentation.